Li-CFG adds an ε-centered gradient penalty to the CFG GAN method and claims this enlarges the discriminator gradient norm, shrinking the latent neighborhood size and thereby increasing image diversity.
IID-GAN: an IID Sampling Perspective for Regularizing Mode Collapse
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Despite its success, generative adversarial networks (GANs) still suffer from mode collapse, i.e., the generator can only map latent variables to a partial set of modes in the target distribution. In this paper, we analyze and seek to regularize this issue with an independent and identically distributed (IID) sampling perspective and emphasize that holding the IID property referring to the target distribution for generation can naturally avoid mode collapse. This is based on the basic IID assumption for real data in machine learning. However, though the source samples {z} obey IID, the generations {G(z)} may not necessarily be IID sampling from the target distribution. Based on this observation, considering a necessary condition of IID generation that the inverse samples from target data should also be IID in the source distribution, we propose a new loss to encourage the closeness between inverse samples of real data and the Gaussian source in latent space to regularize the generation to be IID from the target distribution. Experiments on both synthetic and real-world data show the effectiveness of our model.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
A New Formulation of Lipschitz Constrained With Functional Gradient Learning for GANs
Li-CFG adds an ε-centered gradient penalty to the CFG GAN method and claims this enlarges the discriminator gradient norm, shrinking the latent neighborhood size and thereby increasing image diversity.